davanstrien
/

numind_generic-entity_recognition_NER-multilingual-v1_wikiann_de

Token Classification

named-entity-recognition

generated_from_span_marker_trainer

Model card Files Files and versions Metrics Training metrics Community

numind_generic-entity_recognition_NER-multilingual-v1_wikiann_de / tokenizer_config.json

davanstrien's picture

davanstrien HF staff

End of training

cb798e4 7 months ago

raw history blame contribute delete

No virus

1.59 kB

	{
	"add_prefix_space": true,
	"added_tokens_decoder": {
	"0": {
	"content": "[PAD]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"100": {
	"content": "[UNK]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"101": {
	"content": "[CLS]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"102": {
	"content": "[SEP]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"103": {
	"content": "[MASK]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"119547": {
	"content": "<start>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"119548": {
	"content": "<end>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"clean_up_tokenization_spaces": true,
	"cls_token": "[CLS]",
	"do_lower_case": false,
	"entity_max_length": 9,
	"mask_token": "[MASK]",
	"model_max_length": 256,
	"pad_token": "[PAD]",
	"sep_token": "[SEP]",
	"strip_accents": null,
	"tokenize_chinese_chars": true,
	"tokenizer_class": "BertTokenizer",
	"unk_token": "[UNK]"
	}